MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912473103204352 |
|---|---|
| author | Liu, Ziyan Fan, Chunxiao Lou, Haoran Wu, Yuexin Deng, Kaiwei |
| author_facet | Liu, Ziyan Fan, Chunxiao Lou, Haoran Wu, Yuexin Deng, Kaiwei |
| contents | The rapid expansion of memes on social media has highlighted the urgent need for effective approaches to detect harmful content. However, traditional data-driven approaches struggle to detect new memes due to their evolving nature and the lack of up-to-date annotated data. To address this issue, we propose MIND, a multi-agent framework for zero-shot harmful meme detection that does not rely on annotated data. MIND implements three key strategies: 1) We retrieve similar memes from an unannotated reference set to provide contextual information. 2) We propose a bi-directional insight derivation mechanism to extract a comprehensive understanding of similar memes. 3) We then employ a multi-agent debate mechanism to ensure robust decision-making through reasoned arbitration. Extensive experiments on three meme datasets demonstrate that our proposed framework not only outperforms existing zero-shot approaches but also shows strong generalization across different model architectures and parameter scales, providing a scalable solution for harmful meme detection. The code is available at https://github.com/destroy-lonely/MIND. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06908 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection Liu, Ziyan Fan, Chunxiao Lou, Haoran Wu, Yuexin Deng, Kaiwei Computation and Language Artificial Intelligence The rapid expansion of memes on social media has highlighted the urgent need for effective approaches to detect harmful content. However, traditional data-driven approaches struggle to detect new memes due to their evolving nature and the lack of up-to-date annotated data. To address this issue, we propose MIND, a multi-agent framework for zero-shot harmful meme detection that does not rely on annotated data. MIND implements three key strategies: 1) We retrieve similar memes from an unannotated reference set to provide contextual information. 2) We propose a bi-directional insight derivation mechanism to extract a comprehensive understanding of similar memes. 3) We then employ a multi-agent debate mechanism to ensure robust decision-making through reasoned arbitration. Extensive experiments on three meme datasets demonstrate that our proposed framework not only outperforms existing zero-shot approaches but also shows strong generalization across different model architectures and parameter scales, providing a scalable solution for harmful meme detection. The code is available at https://github.com/destroy-lonely/MIND. |
| title | MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.06908 |